id: 088
narrative_anchor_date: '2028-01-01'
test: Create a historical evidence card for the incomplete-setup reminder's October 6-18, 2027 initial
  production interval. Reconcile every evaluation outcome, record the agreement and incident-control results,
  and state what the interval did and did not decide.
load_bearing_facts:
- 289
- 290
- 291
expected_tool_calls:
- create_doc
grade:
  type: tool_trace
  config:
    check_version: 2
    today: '2028-01-01'
    semantic_judge_version: 2
    assertions:
    - type: field_equals
      tool: create_doc
      action_id: create_initial_interval_card
      path: result.ok
      value: true
      check_id: riley_088_00
    - type: field_llm_judge
      tool: create_doc
      action_id: create_initial_interval_card
      path: args
      criterion: The card says Owen closed the October 6-18, 2027 interval. It reconciles 3,240 fresh
        evaluations into 412 displays, 138 suppressions for active Customer Success work, 61 holds for
        missing, stale, unresolved, or conflicting state, and 2,629 non-displays because the incomplete-setup
        or qualifying-human-admin condition was not met. Reporting, lifecycle, and reminder outcomes agreed
        throughout, with no customer correction, incident stop, source-age breach, rollback, or need for
        rollback. The interval supplied evidence for a separate rollout decision but did not make that
        decision.
      check_id: riley_088_01
mock_state: {}